Security audit

论文常用的tex格式转换为word格式，核心是能转换数学公式（非图片），表格，图表等等

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly performs local LaTeX-to-DOCX conversion, but it silently inserts a fixed company, location, and email block into every generated document.

Review carefully before installing. The main risk is not system compromise; it is document integrity. Any DOCX produced by this version may include an unrelated company, location, and email address unless the script is changed. Install dependencies in a virtual environment and prefer pinned package versions.

A.I.G

Vulnerability Patterns

Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review

Findings (2)

T04 · Embedded Malicious Code

Error

Location: scripts/tex2docx.py:257
Finding: Undisclosed Hardcoded Identity Injection into Generated Documents
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:11
Finding: Unpinned Executable Python Dependencies
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: If the underlying code injects hard-coded contact or affiliation text into the generated DOCX that is not sourced from the input .tex, the skill is silently altering document content beyond its declared conversion role. In an academic-paper workflow, this can misrepresent authorship or insert unauthorized content into formal documents, which is especially risky because users may trust the output as a faithful conversion.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: If the underlying code injects hard-coded contact or affiliation text into the generated DOCX that is not sourced from the input .tex, the skill is silently altering document content beyond its declared conversion role. In an academic-paper workflow, this can misrepresent authorship or insert unauthorized content into formal documents, which is especially risky because users may trust the output as a faithful conversion.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The script unconditionally inserts a hard-coded affiliation and email into every generated document, even though the skill’s purpose is only to convert user-supplied LaTeX to DOCX. This is unauthorized content injection that can exfiltrate the operator’s identity into user documents, misattribute authorship, and act as a covert watermark or spam payload; in an automated document-generation workflow, users may distribute the tainted output without noticing.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.